> For the complete documentation index, see [llms.txt](https://doc.batch.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.batch.com/guides-and-best-practices/batch-ai.md).

# Batch AI

- [How to leverage Batch connectivity via MCP?](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-leverage-batch-connectivity-via-mcp.md)
- [How to Measure the Performance of Batch AI Predict Scores?](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-measure-the-performance-of-batch-ai-predict-scores.md): Learn how to measure the real impact of Batch AI Predict scores using two test methods you can run directly in Batch. No external tooling required.
- [How to Send Every Message at the Moment Each Customer Is Most Likely to Engage?](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-send-every-message-at-the-moment-each-customer-is-most-likely-to-engage.md): This guide explains how to use the Best Send Time score from Batch AI Predict to automatically send each customer their message at the time of day they are most likely to open and act on it.
- [How to Target the Right Customers for Every Product Campaign?](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-target-the-right-customers-for-every-product-campaign.md): This guide explains how to use the Product Propensity score from Batch AI Predict. Stop sending product campaigns to your entire database. Reach only the customers who are genuinely interested.
- [How to Personalize Your Campaigns with Product Recommendations](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-personalize-your-campaigns-with-product-recommendations.md): This guide explains how to use the Product Recommendation score from Batch AI Predict to show each customer the products they are most likely to buy and move beyond generic bestseller lists.
- [How to Identify and Retain Customers at Risk of Cancelling Their Subscription](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-identify-and-retain-customers-at-risk-of-cancelling-their-subscription.md): This guide explains how to use the Subscription Churn score from Batch AI Predict to detect customers likely to cancel their subscription before it ends, and act before it happens.
- [How to Retain Your Best Customers Before It's Too Late](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-retain-your-best-customers-before-its-too-late.md): This guide explains how to use the At-risk top customer score from Batch AI Predict to identify your most valuable customers before they churn and act while there is still time.
- [How to Time Your Reactivation Campaigns Around Each Customer's Predicted Churn Date](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-time-your-reactivation-campaigns-around-each-customers-predicted-churn-date.md): This guide explains how to use the Decisive Churn Date score from Batch AI Predict to predict when each customer is likely to become inactive, and trigger retention actions at exactly the right moment
- [How to Personalize Promotions Based on Each Customer's Price Sensitivity](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-personalize-promotions-based-on-each-customers-price-sensitivity.md): This guide explains how to use the Promotion Sensitivity score to identify which customers actually need a discount to convert, and stop offering promotions to those who would have purchased anyway.
- [How to Personalize Promotions with the Right Discount Level for Each Customer](https://doc.batch.com/guides-and-best-practices/batch-ai/how-to-personalize-promotions-with-the-right-discount-level-for-each-customer.md): This guide explains how to use the Promotion Recommendation score from Batch AI Predict to automatically determine the most effective discount level for each customer, maximizing both conversion and m


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://doc.batch.com/guides-and-best-practices/batch-ai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.